Task processing method

Abstract

The embodiment of the invention provides a task processing method, and the method comprises the steps: obtaining a target to-be-processed task, and obtaining a user set; determining user attribute information corresponding to each user in the user set; based on the user attribute information corresponding to each user, predicting a prediction processing result of processing the target to-be-processed task by each user; and sorting the users based on the prediction processing result, determining a target user, and sending the target to-be-processed task to the target user.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the technical field of computer technology, and particularly relate to a task processing method. BACKGROUND

[0002] With the continuous development of computer technology, in the process of promoting the target object, in order to improve the promotion effect, the target promoter is usually used to promote the target object.

[0003] However, in the case of multiple promoters, the promotion effect of multiple promoters is usually evaluated by manual evaluation, so as to determine the target promoter. The manual evaluation method has low evaluation efficiency and is difficult to guarantee the promotion effect of the target object by the target promoter. SUMMARY Therefore, the embodiments of the present specification provide a task processing method. One or more embodiments of the present specification also relate to a task processing apparatus, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects in the prior art.

[0004] According to a first aspect of the embodiments of the present specification, a task processing method is provided, comprising: obtaining a target to-be-processed task and obtaining a user set; determining user attribute information corresponding to each user in the user set; based on the user attribute information corresponding to each user, predicting a predicted processing result of each user processing the target to-be-processed task; based on the predicted processing result, sorting each user, determining a target user, and sending the target to-be-processed task to the target user.

[0005] According to a second aspect of the embodiments of the present specification, a task processing apparatus is provided, comprising: an obtaining unit configured to obtain a target to-be-processed task and obtain a user set; a determining unit configured to determine user attribute information corresponding to each user in the user set; a prediction unit configured to predict a predicted processing result of each user processing the target to-be-processed task based on the user attribute information corresponding to each user; a processing unit configured to sort each user based on the predicted processing result, determine a target user, and send the target to-be-processed task to the target user.

[0006] According to a third aspect of the embodiments of the present specification, a computing device is provided, comprising: a memory and a processor; The memory is configured to store a computer program or instructions, and the processor is configured to execute the computer program or instructions, and the computer program or instructions, when executed by the processor, implement the steps of the method.

[0007] According to a fourth aspect of an embodiment of the present specification, a computer readable storage medium is provided, which stores a computer program or instructions, and the computer program or instructions, when executed by a processor, implement the steps of the method.

[0008] According to a fifth aspect of an embodiment of the present specification, a computer program product is provided, which includes a computer program or instructions, and the computer program or instructions, when executed by a processor, implement the steps of the method.

[0009] According to the task processing method provided in the present specification, according to the target task to be processed, a user set is determined, and the user attribute information of each user in the user set is analyzed, and the prediction result of each user processing the target task to be processed is predicted. The prediction processing result is sorted, thereby shortening the screening time of the user set, and further reducing the artificial intervention cost. In addition, the prediction processing result is determined according to the user attribute information, thereby improving the screening accuracy of the target user, and further improving the completion quality of the target task to be processed. Further, by predicting the prediction processing result of the target task to be processed, the decision deviation caused by human factors is avoided, and the task processing efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 A flow chart of a task processing method according to an embodiment of the present specification is shown; Figure 2 A processing process schematic diagram of a task processing method according to an embodiment of the present specification is shown; Figure 3 A structural schematic diagram of a task processing device according to an embodiment of the present specification is shown; Figure 4 An architecture diagram of a task processing system according to an embodiment of the present specification is shown; Figure 5 A structural block diagram of a computing device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0011] In the following description, many specific details are set forth in order to provide a thorough understanding of the present specification. However, the present specification can be practiced in many different ways beyond the specific embodiments described herein, and it is understood that persons having ordinary skill in the art can make similar modifications without departing from the scope of the present specification.

[0012] The terminology used in this disclosure of one or more embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of one or more embodiments of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0013] It will be understood that, although the terms first, second, etc. can be used herein to describe various information, these terms are not intended to denote a temporal sequence, but are used only to distinguish one piece of information from another. For example, a first can be termed a second, and, similarly, a second can be termed a first, without departing from the scope of one or more embodiments of the present disclosure. Depending on the context, the word "if' as used herein can be interpreted to mean "when" or "in response to determining" or "in response to a determination."

[0014] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present disclosure are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards in the relevant region, and provide corresponding operation portal for user to choose authorization or refusal.

[0015] In one or more embodiments of the present disclosure, a large model refers to a deep learning model with a large number of model parameters, usually containing hundreds of millions, tens of billions, hundreds of billions, thousands of billions or even tens of thousands of billions of model parameters. The large model can also be called a cornerstone model or a foundation model. Through large-scale unlabeled corpus pre-training of the large model, a pre-trained model with hundreds of millions of parameters is produced. Such a model can adapt to a wide range of downstream tasks and has good generalization ability. For example, a large-scale language model (LLM) and a multi-modal pre-training model.

[0016] In practical applications, large models only require a small number of samples to fine-tune the pre-trained model before they can be applied to different tasks. Large models can be widely used in fields such as Natural Language Processing (NLP) and Computer Vision. Specifically, they can be applied to computer vision tasks such as Visual Question Answering (VQA), Image Captioning (IC), and Image Generation, as well as NLP tasks such as text-based sentiment classification, text summarization, and machine translation. The main application scenarios for large models include digital assistants, intelligent robots, search, online education, office software, e-commerce, and intelligent design.

[0017] The task processing method involved in this application is applied to scenarios where a target object is being promoted. For example, in an e-commerce platform, a team leader processes a specific product as a pending task set by the task publisher.

[0018] First, the relevant terms used in this application will be explained.

[0019] A group leader is a user who promotes products. During a specific time period, there is a one-to-one correspondence between the group leader and the product.

[0020] With the continuous development of computer technology, during the process of group leaders promoting to target groups, different group leaders can sign up to process the same target group. Different target groups can be processed by the same group leader at different time periods. Therefore, when multiple group leaders choose to process the same target group, in order to accurately determine the target group leader to process the target group, a manual screening method is usually used to screen multiple users. This leads to the selection of target users being influenced by human factors.

[0021] Therefore, this specification provides a task processing method, and also relates to a task processing apparatus, a computing device, a computer-readable storage medium, and a computer program product, which will be described in detail in the following embodiments.

[0022] See Figure 1 , Figure 1 A flowchart of a task processing method according to an embodiment of this specification is shown, specifically including the following steps 102-108.

[0023] Step 102: Obtain the target tasks to be processed and obtain the user set.

[0024] In an embodiment provided by the present application, a target to-be-processed task corresponding to a target object is acquired, and a user set corresponding to the target to-be-processed task is acquired.

[0025] The target to-be-processed task can be understood as a to-be-processed task associated with the target object for the purpose of improving exposure of the target object, and the to-be-processed task is generated by a user associated with the target object. The user set can be understood as a candidate user group performing the target to-be-processed task for the purpose of promoting the execution progress of the target to-be-processed task, and is an optional range of distribution of the target to-be-processed task.

[0026] It should be understood that the user generating the target to-be-processed task in the present application is not the same as the user in the user set. Further, the user generating the target to-be-processed task can be understood as a task publisher, and the user in the user set can be understood as a task performer processing the target to-be-processed task. For ease of description, the task performer is represented by a user in the present specification.

[0027] Further, taking the target object as a transaction object with supply value as an example, the above content can be understood as that the task publisher generates the target to-be-processed task according to the supply value of the target object, and acquires a user set composed of task performers for the purpose of improving exposure of the target object to obtain resource value of the task performers.

[0028] Further, based on the above content, the relationship between the target to-be-processed task corresponding to the target object and the user in the user set can be understood as that one target to-be-processed task corresponds to multiple users. However, in the process of processing the target to-be-processed task, the relationship between the target to-be-processed task and the user is a one-to-one relationship.

[0029] For ease of understanding, the present application uses the following method to acquire the target to-be-processed task and the user set.

[0030] It should be understood that the task processing method provided by the present application can be understood as being applied to a task processing platform for generating a target to-be-processed task by a task publisher for a target object, and executing the target to-be-processed task by a user.

[0031] On this basis, in order to improve the processing safety of the target to-be-processed task, the present application can pre-authenticate at least one user applying to reside in the task processing platform, and only retain the users passing the authentication in the task processing platform.

[0032] In an embodiment provided by the present application, creating a target to-be-processed task includes: acquiring an initial to-be-processed task corresponding to a target object; determine value information of the target object based on the initial to-be-processed task; In a case where the value information meets a set condition, determine the initial to-be-processed task as a target to-be-processed task. In a case where the value information does not meet the set condition, adjust the initial to-be-processed task until the value information meets the set condition, to obtain a target to-be-processed task.

[0033] The initial to-be-processed task includes promotion time, supply value, and to-be-promoted quantity of the target object. The target object can be understood as an object or carrier of the to-be-processed task with specific attributes. The value information can be understood as a value that can be achieved by the target object through task processing, which is evaluated according to the initial to-be-processed task, and is used to measure whether the initial to-be-processed task is worth processing. The set condition can be understood as a value standard set by a task publisher, which is used to determine whether the created task has processing significance, so as to filter effective to-be-processed tasks according to the set condition. The target to-be-processed task can be understood as a task that is finally determined to meet the set condition after value information evaluation and adjustment.

[0034] For example, in an e-commerce scenario, the target object can be a to-be-promoted product. On this basis, the to-be-processed task can be a promotion task set for the to-be-promoted product.

[0035] In a specific embodiment provided in the present application, an initial to-be-processed task corresponding to a target object is obtained. According to a task prediction model, the promotion time, supply value, and to-be-promoted quantity of the target object in the initial to-be-processed task are taken as parameters for prediction, to obtain value information predicted by the initial to-be-processed task in the case of the set initial to-be-processed task. The value information is compared with the set condition to determine whether the value information of the initial to-be-processed task meets the set condition. In a case where the set condition is met, the initial to-be-processed task is determined as a target to-be-processed task. In a case where the set condition is not met, the promotion time, supply value, and to-be-promoted quantity of the initial to-be-processed task are adjusted. And according to the adjusted initial to-be-processed task, the value information is predicted again. Until the value information corresponding to the adjusted initial to-be-processed task meets the set condition. The adjusted initial to-be-processed task is determined as a target to-be-processed task.

[0036] The task prediction model can be understood as a large language model, which is used to predict a processing result of a target to-be-processed task processed by a to-be-predicted user.

[0037] According to the above-mentioned embodiments of the present application, the value information of the initial to-be-processed task is predicted, and the initial to-be-processed task is determined as the target to-be-processed task only when the value information meets the set condition. Otherwise, the parameters in the initial to-be-processed task are adjusted to avoid resource consumption on the initial to-be-processed task with no value. The target to-be-processed task is determined according to the set condition, and the determination accuracy of the target to-be-processed task is improved.

[0038] In a specific embodiment provided by the present application, the target to-be-processed task is obtained, and a user set is obtained, including: The target to-be-processed task is created, and application information for the target to-be-processed task is received. The user corresponding to the application information is added to the user set when the application information meets the preset audit condition.

[0039] In a specific embodiment provided by the present application, the target to-be-processed task is created, and application information of the user identified by identity authentication is received. The application information of each user is audited according to the preset audit condition, and the user corresponding to the application information is added to the user set when the audit result meets the audit condition.

[0040] The application information can be understood as information of the user applying to process the target to-be-processed task, and at least includes an application request of the user applying to process the target to-be-processed task, and an expected value of the user expecting to process the target to-be-processed task.

[0041] The preset audit condition can be understood as a condition for auditing whether the user meets the condition of processing the target to-be-processed task. For example, the expected value threshold can be included in the preset audit condition.

[0042] For example, in combination with the above content, the application information of at least one user for the target to-be-processed task is received after the target to-be-processed task and the user are created. The application information of each user for the target to-be-processed task is audited. For example, whether the user participates in the registration of the target to-be-processed task is audited. The user corresponding to the application information is added to the user set when the preset audit condition is met.

[0043] It should be understood that the user set involved in the above examples of the present application is a set of users meeting the preset audit condition.

[0044] On the basis of the above, the process of obtaining the target to-be-processed task and obtaining the user set can be understood as obtaining an initial to-be-processed task created by the task publisher for the target object, which includes parameters such as promotion time of the target object, supply value, and number of tasks to be promoted. The value information that can be achieved when the initial to-be-processed task is completed is analyzed. The value information is matched with the set condition. If the value information meets the set condition, the initial to-be-processed task is directly determined as the target to-be-processed task. If the value information does not meet the set condition, each parameter in the initial to-be-processed task is adjusted, and the value information that can be achieved when the adjusted to-be-processed task is completed is determined. According to the value information, the set condition is further matched until the target to-be-processed task that meets the set condition is obtained. According to the target to-be-processed task, a user who passes the identity authentication and applies to process the target to-be-processed task is determined. The application information of the user is screened according to the preset audit condition, and the user set is obtained.

[0045] Step 104: Determine the user attribute information corresponding to each user in the user set.

[0046] In a specific embodiment provided by the present application, after obtaining the user set corresponding to the target to-be-processed task according to the above, the user attribute information corresponding to each user in the user set is obtained.

[0047] The user attribute information can be understood as processing data of the user in processing historical tasks of the same type as the target to-be-processed task, or expected value of the user in processing the target to-be-processed task.

[0048] For ease of understanding, the present application uses the following way to explain the above example.

[0049] In a specific embodiment provided by the present application, the user attribute information corresponding to each user in the user set is determined, including: Determine a to-be-processed user, and determine the user type of the to-be-processed user, wherein the to-be-processed user is any user in the user set; Obtain the target task type corresponding to the target to-be-processed task; Determine the user attribute information of the to-be-processed user based on the user type of the to-be-processed user and the target task type.

[0050] In a specific embodiment provided by the present application, any user in the user set is selected as a to-be-processed user. The user type of the to-be-processed user is determined, and the target task type of the target to-be-processed task is determined. The user attribute information of the to-be-processed user is determined according to the user type of the to-be-processed user and the target task type.

[0051] Based on the above, the users in the user set formed by the users are divided according to the user types, to obtain the first-type users and the second-type users. According to the user types and the target task type, the user attribute information of the first-type users and the user attribute information of the second-type users are determined respectively.

[0052] The user type can be understood as a type standard for distinguishing whether the to-be-processed user has historical data information. The user type includes the first type and the second type. For example, the user type can be understood as a source of attribute information for distinguishing users, which is determined according to the historical data, ability characteristics, experience accumulation, and the like of the user.

[0053] The user attribute information can be understood as parameter information reflecting the ability of the to-be-processed user to process the target to-be-processed task. Different user types correspond to different user attribute information.

[0054] According to the embodiments provided in the present application, the processing abilities of different user types for the target to-be-processed task are different, and the requirements of different target task types for the to-be-processed user are also different. By matching the target task type and the user type, the interference of irrelevant information on the user attribute information can be avoided.

[0055] For ease of understanding, the present application determines the user attribute information of the to-be-processed user of different user types in the following manner.

[0056] In a specific embodiment provided in the present application, when the user type is the first type, the user attribute information of the to-be-processed user is determined based on the user type of the to-be-processed user and the target task type, including: When the user type of the to-be-processed user is the first type, the expected value of the to-be-processed user for the target to-be-processed task is obtained; Based on the target task type, at least one historical task corresponding to the to-be-processed user is determined; Based on the at least one historical task, historical data information corresponding to the to-be-processed user is determined; Based on the historical data information and the expected value, the user attribute information of the to-be-processed user is determined.

[0057] In a specific implementation provided in the present application, in the case where the user type is the first type, it can be understood that the user of the current type exists historical data information of historical tasks of the same target task type as the target to-be-processed task. On this basis, according to the target task type, historical data information of all historical tasks processed by the to-be-processed user is obtained. The historical data information corresponding to all historical tasks is fused to obtain a historical data fusion feature corresponding to the to-be-processed user under the first type. The historical data fusion feature can represent feedback value information obtained by the to-be-processed user in the process of processing historical tasks of the same target task type, and sale information corresponding to the to-be-processed user, and the like.

[0058] The feedback value information can be understood as the actual value of the to-be-processed user processing the historical task.

[0059] In a specific implementation provided in the present application, in the case where the user type is the second type, the user attribute information of the to-be-processed user is determined based on the user type of the to-be-processed user and the target task type, including: In the case where the user type of the to-be-processed user is the second type, the expected value of the to-be-processed user for the target to-be-processed task is obtained; At least one reference task type corresponding to the target task type is determined based on the target task type, and at least one reference user is determined based on the reference task type and the target task type. The historical data information corresponding to each reference user is obtained. The user attribute information of the to-be-processed user is determined based on each historical data information and the expected value.

[0060] The second type user can be understood as a user who lacks historical processing data related to the target task type and cannot evaluate his ability through his historical performance, which belongs to a new user or a novice user without historical data. In addition, the second type user has no direct reference to the same task record, and the ability of the second type user lacks historical verification and needs to rely on the performance data of similar external users for indirect evaluation.

[0061] The expected value can be understood as a quantitative expression of the subjective willingness, resource plan and expected result of the second type user for the target to-be-processed task. In addition, since the second type user has no historical data, the expected value is key information reflecting the subjective initiative of the second type user.

[0062] The reference task type can be understood as a task type that is highly similar to the core features of the current task and is filtered based on the target task type. For example, in an e-commerce scenario, the reference task type can be understood as a task type that is consistent with the target task type in terms of industry, target, cycle, complexity, and other core dimensions, ensuring that the user data of the reference task is meaningful for the current task.

[0063] The reference user can be understood as a user who has processed the reference task type and has a satisfactory performance, and the historical data of the reference user can be used as a benchmark to evaluate the potential ability of the second type of user. The reference user must meet the requirements of having processed the reference task type and having good historical performance to ensure the reliability of the reference data.

[0064] The user attribute information of the second type of user can be understood as a comprehensive attribute description formed by combining the historical data information of the reference user and the expected value of the second type of user, which is the core input for subsequent prediction of the processing result. The attribute information takes the reference data as the ability baseline and adjusts the evaluation in combination with the actual input plan of the second type of user.

[0065] In a specific embodiment provided by the present application, when the user type is the second type, it can be understood that the current type of user does not have historical data information of a historical task that is the same as the target task type of the target to-be-processed task. On this basis, a reference task type similar to the target task type is obtained according to the target task type, and a reference user is determined according to each reference task corresponding to the reference task type. The historical data information of all reference tasks processed by the reference user is integrated into the historical data information corresponding to the to-be-processed user. The historical data information corresponding to all historical tasks is fused to obtain the historical data fusion features corresponding to the to-be-processed user under the second type.

[0066] Step 106: predicting the predicted processing result of each user processing the target to-be-processed task based on the user attribute information corresponding to each user.

[0067] In a specific embodiment provided by the present application, the user attribute information includes at least one user attribute sub-information.

[0068] The user attribute sub-information can be understood as promotion data of the to-be-processed user processing the target to-be-processed task, feedback information of the target object, and expected value. The feedback information can be understood as a return rate of goods.

[0069] In a specific embodiment provided by the present application, predicting the predicted processing result of each user processing the target to-be-processed task based on the user attribute information corresponding to each user includes: determining a to-be-predicted user, wherein the to-be-predicted user is any user in the user set; quantize the at least one user attribute sub-information of the to-be-predicted user based on a preset quantization rule to obtain at least one quantization information; weight and fuse the at least one quantization information based on a preset weight to obtain a predicted processing result of the to-be-predicted user in processing the target to-be-processed task.

[0070] For example, x represents the promotion data corresponding to the to-be-predicted user, and w 1 represents a first weight corresponding to the promotion data, y represents the feedback information of the to-be-predicted user to the target object, and w 2 represents a second weight corresponding to the feedback information, and z represents the expected value of the to-be-predicted user to the target object, and w 3 represents a third weight corresponding to the expected value.

[0071] On this basis, the weight and fusion of the at least one quantization information based on a preset weight to obtain a predicted processing result S of the to-be-predicted user in processing the target to-be-processed task can be represented as:

[0072] Step 108: Based on the predicted processing result, ranking each user to determine a target user, and sending the target to-be-processed task to the target user. In combination with the above, ranking each to-be-predicted user according to the predicted processing result to obtain a ranking result, for example, ranking from high to low according to the value corresponding to the predicted processing result, determining the to-be-predicted user ranked first as the target user, and sending the target to-be-processed task to the target user.

[0073] Further, in the process of the to-be-predicted user ranked first executing the target to-be-processed task, the execution result of the to-be-predicted user is monitored in real time. If it is detected that the execution result does not match the predicted processing result predicted by the to-be-predicted user ranked first, the to-be-predicted user ranked second is determined as the target user according to the ranking result, and the target to-be-processed task is processed by the to-be-predicted user ranked second.

[0074] According to the embodiments provided in the present application, the user set is determined according to the target to-be-processed task, and the user attribute information of each user in the user set is automatically analyzed, the predicted processing result is ranked, the screening time of the user set is shortened, and the manual intervention cost is reduced. In addition, in the present application, the predicted processing result is quantized according to the user attribute information, thereby improving the screening accuracy of the target user, and further improving the completion quality of the target to-be-processed task. Further, by predicting the predicted processing result of the target to-be-processed task, the decision deviation caused by human factors is avoided, and the task processing efficiency is improved.

[0075] The following is described in conjunction with the accompanyingFigure 2 With the application of the task processing method provided in the specification to the promotion of goods in the task processing platform as an example, the task processing method is further described. Among them, Figure 2 A processing process schematic diagram of a task processing method provided by an embodiment of the specification is shown.

[0076] It should be understood that in the schematic diagram, the user in the above content is represented by the group leader.

[0077] The task publisher creates an initial to-be-processed task for the target product on the platform, and generates value information for the target product. The task processing platform predicts the value information of the target product according to the initial to-be-processed task of the target product. When the predicted value information of the target product does not meet the set conditions, the initial to-be-processed task of the target product is adjusted until the value information corresponding to the adjusted initial to-be-processed task meets the set conditions. At this time, the initial to-be-processed task is determined as the target to-be-processed task.

[0078] In the task processing platform, each group leader initiates a registration application, and the platform performs a qualification audit on the group leader who initiates the registration application, and adds the group leader whose qualification audit meets the audit conditions to the user set. Obtain the user type of each group leader. Determine whether the type of each group leader is the first type. In the case where the type of the group leader is the first type, the processing result of the group leader on the target to-be-processed task is predicted by using a task prediction model. In the case where the type of the group leader is the second type, a reference group leader is determined, and the processing result of the second type group leader on the target to-be-processed task is determined according to the historical data information corresponding to the reference group leader. The way to determine the reference group leader refers to the way to determine the reference user described above.

[0079] According to the processing result, from high to low, generate a group leader ranking. And determine the target group leader. For example, select the group leader ranked first to execute the target to-be-processed task. And real-time monitoring of the actual execution result. If it is detected that the execution result does not match the predicted processing result, the group leader ranked second will execute the target to-be-processed task, and the group leader ranked second will process the target to-be-processed task.

[0080] Corresponding to the above method embodiment, the specification also provides a task processing device embodiment, Figure 3 A structural schematic diagram of a task processing device provided by an embodiment of the specification is shown. As Figure 3 The device comprises: The acquisition unit 302 is configured to acquire a target to-be-processed task and acquire a user set.

[0081] The determination unit 304 is configured to determine the user attribute information corresponding to each user in the user set.

[0082] The prediction unit 306 is configured to predict a predicted processing result of each user processing the target to-be-processed task based on user attribute information corresponding to each user.

[0083] The processing unit 308 is configured to sort each user based on the predicted processing result, determine a target user, and send the target to-be-processed task to the target user. Further, the determination unit 304 is further configured to: determine a to-be-processed user and determine a user type of the to-be-processed user, wherein the to-be-processed user is any user in a user set; obtain a target task type corresponding to the target to-be-processed task; determine user attribute information of the to-be-processed user based on the user type of the to-be-processed user and the target task type.

[0084] Further, the user type includes a first type; the determination unit 304 is further configured to: in a case where the user type of the to-be-processed user is the first type, obtain an expected value of the to-be-processed user for the target to-be-processed task; determine at least one historical task corresponding to the to-be-processed user based on the target task type; determine historical data information corresponding to the to-be-processed user based on the at least one historical task; determine the user attribute information of the to-be-processed user based on the historical data information and the expected value.

[0085] Further, the user type further includes a second type; the determination unit 304 is further configured to: in a case where the user type of the to-be-processed user is the second type, obtain an expected value of the to-be-processed user for the target to-be-processed task; determine at least one reference task type corresponding to the target task type based on the target task type, and determine at least one reference user based on the reference task type and the target task type; obtain historical data information corresponding to each reference user; determine the user attribute information of the to-be-processed user based on each historical data information and the expected value.

[0086] Further, the user attribute information includes at least one user attribute sub-information; the prediction unit 306 is further configured to: determine a to-be-predicted user, wherein the to-be-predicted user is any user in the user set; Quantize at least one user attribute sub-information of the to-be-predicted user based on a preset quantization rule to obtain at least one quantization information. Weighted fuse at least one quantization information based on a preset weight to obtain a predicted processing result of the to-be-predicted user processing the target to-be-processed task.

[0087] Further, the obtaining unit 302 is further configured to: create a target to-be-processed task, and receive application information for the target to-be-processed task; add a user corresponding to the application information to the user set in a case where the application information meets a preset audit condition.

[0088] Further, the obtaining unit 302 is further configured to: obtain an initial to-be-processed task corresponding to a target object; determine value information of the target object based on the initial to-be-processed task; determine the initial to-be-processed task as a target to-be-processed task in a case where the value information meets a set condition; adjust the initial to-be-processed task until the value information meets the set condition to obtain a target to-be-processed task in a case where the value information does not meet the set condition.

[0089] The above is a schematic scheme of the task processing device of the embodiment. It should be noted that the technical scheme of the task processing device and the technical scheme of the task processing method described above belong to the same concept, and the details of the technical scheme of the task processing device which are not described in detail can be referred to the description of the technical scheme of the task processing method.

[0090] Referring to Figure 4 , Figure 4 An architecture diagram of a task processing system is shown, which can include a client 100 and a server 200. The client 100 is configured to send a target to-be-processed task to the server 200. The server 200 is configured to obtain the target to-be-processed task and obtain a user set; determine user attribute information corresponding to each user in the user set; predict a predicted processing result of each user processing the target to-be-processed task based on the user attribute information corresponding to each user; sort each user based on the predicted processing result to determine a target user; and send the target user to the client 100. The client 100 is further configured to receive the target user sent by the server 200.

[0091] The task processing system can include a plurality of clients 100 and a server 200, where the client 100 can be referred to as an end-side device, and the server 200 can be referred to as a cloud-side device. The plurality of clients 100 can establish a communication connection through the server 200. In a task processing scenario, the server 200 is used to provide a task processing service between the plurality of clients 100. The plurality of clients 100 can respectively act as a sending end or a receiving end to implement communication through the server 200.

[0092] A user can interact with the server 200 through the client 100 to receive data sent by another client 100, or send data to another client 100, and the like. In a task processing scenario, the user can publish a data stream to the server 200 through the client 100. The server 200 generates a task processing according to the data stream, and pushes the task processing to other clients that establish a communication connection.

[0093] The client 100 and the server 200 establish a connection through a network. The network provides a medium for a communication link between the client 100 and the server 200. The network can include various connection types, such as a wired, wireless communication link, or a fiber cable, and the like. The data transmitted by the client 100 can need to be processed through encoding, transcoding, compression, and the like before being published to the server 200.

[0094] The client 100 can be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5) application, or a light application (also referred to as a small program, a lightweight application program), or a cloud application, and the like. The client 100 can be developed based on a software development kit (SDK) provided by the server 200, such as an RTC (Real Time Communication) SDK. The client 100 can be deployed in a computing device, and needs to depend on a device or an APP in the device to run, and the like. The computing device can have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, and the like. Various other applications can also be configured in the computing device, such as a man-machine dialogue application, a model training application, a text processing application, a web browser application, a shopping application, a search application, an instant communication tool, an email client, a social platform software, and the like.

[0095] The server 200 can include a server providing various services, for example, a server providing a communication service for a plurality of clients, for example, a server for background training providing support for a model used on a client, for example, a server processing data sent by a client, and the like. It should be noted that the server 200 can be implemented as a distributed server cluster composed of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server of a cloud service, a cloud database, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN, Content Delivery Network), and big data and artificial intelligence platforms, and the like basic cloud computing services, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0096] It should be noted that the task processing method provided in the embodiments of the present specification is generally executed by the server, but in other embodiments of the present specification, the client can also have similar functions as the server, so as to execute the task processing method provided in the embodiments of the present specification. In other embodiments, the task processing method provided in the embodiments of the present specification can also be executed by the client and the server together.

[0097] Figure 5 A structural block diagram of a computing device according to an embodiment of the present application is shown. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. The processor 520 is connected to the memory 510 through a bus 530, and a database 550 is used to save data.

[0098] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of such networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or combinations of such networks, such as the Internet. The access device 540 can include one or more of any type of network interface (for example, a network interface card (NIC)) such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC) interface, or the like.

[0099] In one embodiment of the present application, the above-mentioned components of the computing device 500, as well as other components not shown in FIG. 5, can be connected to each other by a bus. It should be understood that Figure 5 Figure 5 The computing device structure diagram shown is merely for the purpose of example, and is not a limitation on the scope of the present application. Other components can be added or replaced by those skilled in the art as needed.

[0100] The computing device 500 can be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (for example, a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, and the like), a mobile phone (for example, a smartphone), a wearable computing device (for example, a smart watch, smart glasses, and the like), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 500 can also be a mobile or stationary server.

[0101] The processor 520 is configured to execute computer programs or instructions that implement the steps of the above-mentioned task processing method when executed by the processor.

[0102] ​The above is a schematic scheme of the computing device of the embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the task processing method described above belong to the same concept, and the details of the technical scheme of the computing device that are not described in detail can be referred to the description of the technical scheme of the task processing method.

[0103] An embodiment of the present specification also provides a computer readable storage medium storing a computer program or instructions, which, when executed by a processor, implement the steps of the task processing method described above.

[0104] Each of the embodiments in the present specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the difference from other embodiments. In particular, for the computer readable storage medium embodiment, since it is basically similar to the task processing method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the task processing method embodiment.

[0105] An embodiment of the present specification also provides a computer program product comprising a computer program or instructions, which, when executed by a processor, implement the steps of the task processing method described above.

[0106] The above is a schematic scheme of the computer program product of the embodiment. It should be noted that the technical scheme of the computer program product and the technical scheme of the task processing method described above belong to the same concept, and the details of the technical scheme of the computer program product that are not described in detail can be referred to the description of the technical scheme of the task processing method.

[0107] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than the order described in the embodiments and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order in order to achieve the desired results. In some implementations, multitasking and parallel processing can be advantageous.

[0108] The computer readable medium can include any entity or apparatus capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the computer readable medium can include appropriate additions or subtractions according to the requirements of patent practice. For example, according to the patent practice in some regions, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0109] It should be noted that the above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve the desired result. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired result. In some embodiments, multi-task processing and parallel processing are possible or advantageous. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of the specification.

[0110] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0111] The preferred embodiments of the present specification disclosed above are only used to help explain the present specification. The alternative embodiments do not describe all the details and limit the invention to the specific embodiments described. Obviously, according to the content of the embodiments of the present specification, many modifications and changes can be made. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of the present specification, so that those skilled in the art can well understand and use the present specification. The present specification is limited by the claims and their full scope and equivalents.

Claims

1. A task processing method, comprising: obtaining a target to-be-processed task and a user set; determining user attribute information corresponding to each user in the user set; predicting a predicted processing result of each user processing the target to-be-processed task based on the user attribute information corresponding to each user; sorting each user based on the predicted processing result, determining a target user, and sending the target to-be-processed task to the target user.

2. The method of claim 1, wherein determining user attribute information corresponding to each user in the user set comprises: determining a to-be-processed user and a user type of the to-be-processed user, wherein the to-be-processed user is any user in the user set; obtaining a target task type corresponding to the target to-be-processed task; determining user attribute information of the to-be-processed user based on the user type of the to-be-processed user and the target task type.

3. The method of claim 2, wherein the user type comprises a first type; determining user attribute information of the to-be-processed user based on the user type of the to-be-processed user and the target task type comprises: in a case where the user type of the to-be-processed user is the first type, obtaining an expected value of the to-be-processed user for the target to-be-processed task; determining at least one historical task corresponding to the to-be-processed user based on the target task type; determining historical data information corresponding to the to-be-processed user based on the at least one historical task; determining user attribute information of the to-be-processed user based on the historical data information and the expected value.

4. The method of claim 2, wherein the user type further comprises a second type; determining user attribute information of the to-be-processed user based on the user type of the to-be-processed user and the target task type comprises: in a case where the user type of the to-be-processed user is the second type, obtaining an expected value of the to-be-processed user for the target to-be-processed task; determining at least one reference task type corresponding to the target task type based on the target task type, and determining at least one reference user based on the reference task type and the target task type; obtaining historical data information corresponding to each reference user; determining user attribute information of the to-be-processed user based on each historical data information and the expected value.

5. The method of any one of claims 1 to 4, wherein the user attribute information comprises at least one user attribute sub-information; predicting a predicted processing result of each user processing the target to-be-processed task based on the user attribute information corresponding to each user comprises: determining a to-be-predicted user, wherein the to-be-predicted user is any user in the user set; quantifying at least one user attribute sub-information of the to-be-predicted user based on a preset quantification rule to obtain at least one quantification information; weighting and fusing the at least one quantification information based on a preset weight to obtain a predicted processing result of the to-be-predicted user processing the target to-be-processed task.

6. The method of claim 1, wherein obtaining a target to-be-processed task and a user set comprises: create a target to-be-processed task, and receive application information for the target to-be-processed task; in a case where the application information meets preset audit conditions, add a user corresponding to the application information to a user set. 7.The method of claim 6, wherein creating the target to-be-processed task comprises: obtaining an initial to-be-processed task corresponding to the target object; determining value information of the target object based on the initial to-be-processed task; in a case where the value information meets set conditions, determining the initial to-be-processed task as the target to-be-processed task; in a case where the value information does not meet the set conditions, adjusting the initial to-be-processed task until the value information meets the set conditions to obtain the target to-be-processed task. 8.A computing device comprising: a memory and a processor; the memory is configured to store a computer program or instructions, and the processor is configured to execute the computer program or instructions, and the computer program or instructions, when executed by the processor, implement the steps of the method of any one of claims 1 to 7. 9.A computer-readable storage medium storing a computer program or instructions, and the computer program or instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 7. 10.A computer program product comprising a computer program or instructions, and the computer program or instructions, when executed by a processor, implement the steps of the method of any one of claims 1 to 7.

Images